6.6.79-rc1 review

@@ -661,6 +661,9 @@ struct md_personality
 	void *(*takeover) (struct mddev *mddev);
 	/* Changes the consistency policy of an active array. */
 	int (*change_consistency_policy)(struct mddev *mddev, const char *buf);
+	/* convert io ranges from array to bitmap */
+	void (*bitmap_sector)(struct mddev *mddev, sector_t *offset,
+			      unsigned long *sectors);
 };
 
 struct md_sysfs_entry {

@@ -5996,6 +5996,54 @@ static enum reshape_loc get_reshape_loc(
 	return LOC_BEHIND_RESHAPE;
 }
 
+static void raid5_bitmap_sector(struct mddev *mddev, sector_t *offset,
+				unsigned long *sectors)
+{
+	struct r5conf *conf = mddev->private;
+	sector_t start = *offset;
+	sector_t end = start + *sectors;
+	sector_t prev_start = start;
+	sector_t prev_end = end;
+	int sectors_per_chunk;
+	enum reshape_loc loc;
+	int dd_idx;
+
+	sectors_per_chunk = conf->chunk_sectors *
+		(conf->raid_disks - conf->max_degraded);
+	start = round_down(start, sectors_per_chunk);
+	end = round_up(end, sectors_per_chunk);
+
+	start = raid5_compute_sector(conf, start, 0, &dd_idx, NULL);
+	end = raid5_compute_sector(conf, end, 0, &dd_idx, NULL);
+
+	/*
+	 * For LOC_INSIDE_RESHAPE, this IO will wait for reshape to make
+	 * progress, hence it's the same as LOC_BEHIND_RESHAPE.
+	 */
+	loc = get_reshape_loc(mddev, conf, prev_start);
+	if (likely(loc != LOC_AHEAD_OF_RESHAPE)) {
+		*offset = start;
+		*sectors = end - start;
+		return;
+	}
+
+	sectors_per_chunk = conf->prev_chunk_sectors *
+		(conf->previous_raid_disks - conf->max_degraded);
+	prev_start = round_down(prev_start, sectors_per_chunk);
+	prev_end = round_down(prev_end, sectors_per_chunk);
+
+	prev_start = raid5_compute_sector(conf, prev_start, 1, &dd_idx, NULL);
+	prev_end = raid5_compute_sector(conf, prev_end, 1, &dd_idx, NULL);
+
+	/*
+	 * for LOC_AHEAD_OF_RESHAPE, reshape can make progress before this IO
+	 * is handled in make_stripe_request(), we can't know this here hence
+	 * we set bits for both.
+	 */
+	*offset = min(start, prev_start);
+	*sectors = max(end, prev_end) - *offset;
+}
+
 static enum stripe_result make_stripe_request(struct mddev *mddev,
 		struct r5conf *conf, struct stripe_request_ctx *ctx,
 		sector_t logical_sector, struct bio *bi)

@@ -9099,6 +9147,7 @@ static struct md_personality raid6_perso
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.bitmap_sector  = raid5_bitmap_sector,
 };
 static struct md_personality raid5_personality =
 {

@@ -9124,6 +9173,7 @@ static struct md_personality raid5_perso
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.bitmap_sector  = raid5_bitmap_sector,
 };
 
 static struct md_personality raid4_personality =

@@ -9150,6 +9200,7 @@ static struct md_personality raid4_perso
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid4_takeover,
 	.change_consistency_policy = raid5_change_consistency_policy,
+	.bitmap_sector  = raid5_bitmap_sector,
 };
 
 static int __init raid5_init(void)

@@ -1517,7 +1517,6 @@ int md_bitmap_startwrite(struct bitmap *
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(md_bitmap_startwrite);
 
 void md_bitmap_endwrite(struct bitmap *bitmap, sector_t offset,
 			unsigned long sectors)

@@ -1564,7 +1563,6 @@ void md_bitmap_endwrite(struct bitmap *b
 			sectors = 0;
 	}
 }
-EXPORT_SYMBOL_GPL(md_bitmap_endwrite);
 
 static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks,
 			       int degraded)

@@ -8713,12 +8713,32 @@ void md_submit_discard_bio(struct mddev
 }
 EXPORT_SYMBOL_GPL(md_submit_discard_bio);
 
+static void md_bitmap_start(struct mddev *mddev,
+			    struct md_io_clone *md_io_clone)
+{
+	if (mddev->pers->bitmap_sector)
+		mddev->pers->bitmap_sector(mddev, &md_io_clone->offset,
+					   &md_io_clone->sectors);
+
+	md_bitmap_startwrite(mddev->bitmap, md_io_clone->offset,
+			     md_io_clone->sectors);
+}
+
+static void md_bitmap_end(struct mddev *mddev, struct md_io_clone *md_io_clone)
+{
+	md_bitmap_endwrite(mddev->bitmap, md_io_clone->offset,
+			   md_io_clone->sectors);
+}
+
 static void md_end_clone_io(struct bio *bio)
 {
 	struct md_io_clone *md_io_clone = bio->bi_private;
 	struct bio *orig_bio = md_io_clone->orig_bio;
 	struct mddev *mddev = md_io_clone->mddev;
 
+	if (bio_data_dir(orig_bio) == WRITE && mddev->bitmap)
+		md_bitmap_end(mddev, md_io_clone);
+
 	if (bio->bi_status && !orig_bio->bi_status)
 		orig_bio->bi_status = bio->bi_status;
 

@@ -8743,6 +8763,12 @@ static void md_clone_bio(struct mddev *m
 	if (blk_queue_io_stat(bdev->bd_disk->queue))
 		md_io_clone->start_time = bio_start_io_acct(*bio);
 
+	if (bio_data_dir(*bio) == WRITE && mddev->bitmap) {
+		md_io_clone->offset = (*bio)->bi_iter.bi_sector;
+		md_io_clone->sectors = bio_sectors(*bio);
+		md_bitmap_start(mddev, md_io_clone);
+	}
+
 	clone->bi_end_io = md_end_clone_io;
 	clone->bi_private = md_io_clone;
 	*bio = clone;

@@ -746,6 +746,8 @@ struct md_io_clone {
 	struct mddev	*mddev;
 	struct bio	*orig_bio;
 	unsigned long	start_time;
+	sector_t	offset;
+	unsigned long	sectors;
 	struct bio	bio_clone;
 };
 

@@ -421,9 +421,6 @@ static void close_write(struct r1bio *r1
 	}
 	if (test_bit(R1BIO_BehindIO, &r1_bio->state))
 		md_bitmap_end_behind_write(r1_bio->mddev);
-	/* clear the bitmap if all writes complete successfully */
-	md_bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
-			   r1_bio->sectors);
 	md_write_end(r1_bio->mddev);
 }
 

@@ -1517,8 +1514,6 @@ static void raid1_write_request(struct m
 
 			if (test_bit(R1BIO_BehindIO, &r1_bio->state))
 				md_bitmap_start_behind_write(mddev);
-			md_bitmap_startwrite(bitmap, r1_bio->sector,
-					     r1_bio->sectors);
 			first_clone = 0;
 		}
 

@@ -427,9 +427,6 @@ static void raid10_end_read_request(stru
 
 static void close_write(struct r10bio *r10_bio)
 {
-	/* clear the bitmap if all writes complete successfully */
-	md_bitmap_endwrite(r10_bio->mddev->bitmap, r10_bio->sector,
-			   r10_bio->sectors);
 	md_write_end(r10_bio->mddev);
 }
 

@@ -1541,7 +1538,6 @@ static void raid10_write_request(struct
 	md_account_bio(mddev, &bio);
 	r10_bio->master_bio = bio;
 	atomic_set(&r10_bio->remaining, 1);
-	md_bitmap_startwrite(mddev->bitmap, r10_bio->sector, r10_bio->sectors);
 
 	for (i = 0; i < conf->copies; i++) {
 		if (r10_bio->devs[i].bio)

@@ -313,8 +313,6 @@ void r5c_handle_cached_data_endio(struct
 		if (sh->dev[i].written) {
 			set_bit(R5_UPTODATE, &sh->dev[i].flags);
 			r5c_return_dev_pending_writes(conf, &sh->dev[i]);
-			md_bitmap_endwrite(conf->mddev->bitmap, sh->sector,
-					   RAID5_STRIPE_SECTORS(conf));
 		}
 	}
 }

110 lines not on this page · raw message

@@ -371,9 +371,6 @@ enum {
 	STRIPE_ON_RELEASE_LIST,
 	STRIPE_BATCH_READY,
 	STRIPE_BATCH_ERR,
-	STRIPE_BITMAP_PENDING,	/* Being added to bitmap, don't add
-				 * to batch yet.
-				 */
 	STRIPE_LOG_TRAPPED,	/* trapped into log (see raid5-cache.c)
 				 * this bit is used in two scenarios:
 				 *

@@ -2762,6 +2762,13 @@ static const struct arm64_cpu_capabiliti
 		.matches = match,						\
 	}
 
+#define HWCAP_CAP_MATCH_ID(match, reg, field, min_value, cap_type, cap)		\
+	{									\
+		__HWCAP_CAP(#cap, cap_type, cap)				\
+		HWCAP_CPUID_MATCH(reg, field, min_value) 			\
+		.matches = match,						\
+	}
+
 #ifdef CONFIG_ARM64_PTR_AUTH
 static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = {
 	{

@@ -2790,6 +2797,13 @@ static const struct arm64_cpu_capabiliti
 };
 #endif
 
+#ifdef CONFIG_ARM64_SVE
+static bool has_sve_feature(const struct arm64_cpu_capabilities *cap, int scope)
+{
+	return system_supports_sve() && has_user_cpuid_feature(cap, scope);
+}
+#endif
+
 static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL),
 	HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES),

@@ -2827,18 +2841,18 @@ static const struct arm64_cpu_capabiliti
 	HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT),
 #ifdef CONFIG_ARM64_SVE
 	HWCAP_CAP(ID_AA64PFR0_EL1, SVE, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE),
-	HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1),
-	HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2),
-	HWCAP_CAP(ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
-	HWCAP_CAP(ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
-	HWCAP_CAP(ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM),
-	HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16),
-	HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16),
-	HWCAP_CAP(ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3),
-	HWCAP_CAP(ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4),
-	HWCAP_CAP(ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM),
-	HWCAP_CAP(ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM),
-	HWCAP_CAP(ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM),
 #endif
 	HWCAP_CAP(ID_AA64PFR1_EL1, SSBS, SSBS2, CAP_HWCAP, KERNEL_HWCAP_SSBS),
 #ifdef CONFIG_ARM64_BTI

@@ -1946,14 +1946,14 @@ struct page *get_dump_page(unsigned long
 /*
  * Returns the number of collected pages. Return value is always >= 0.
  */
-static unsigned long collect_longterm_unpinnable_pages(
+static void collect_longterm_unpinnable_pages(
 					struct list_head *movable_page_list,
 					unsigned long nr_pages,
 					struct page **pages)
 {
-	unsigned long i, collected = 0;
 	struct folio *prev_folio = NULL;
 	bool drain_allow = true;
+	unsigned long i;
 
 	for (i = 0; i < nr_pages; i++) {
 		struct folio *folio = page_folio(pages[i]);

@@ -1965,8 +1965,6 @@ static unsigned long collect_longterm_un
 		if (folio_is_longterm_pinnable(folio))
 			continue;
 
-		collected++;
-
 		if (folio_is_device_coherent(folio))
 			continue;
 

@@ -1988,8 +1986,6 @@ static unsigned long collect_longterm_un
 				    NR_ISOLATED_ANON + folio_is_file_lru(folio),
 				    folio_nr_pages(folio));
 	}
-
-	return collected;
 }
 
 /*

@@ -2082,12 +2078,10 @@ err:
 static long check_and_migrate_movable_pages(unsigned long nr_pages,
 					    struct page **pages)
 {
-	unsigned long collected;
 	LIST_HEAD(movable_page_list);
 
-	collected = collect_longterm_unpinnable_pages(&movable_page_list,
-						nr_pages, pages);
-	if (!collected)
+	collect_longterm_unpinnable_pages(&movable_page_list, nr_pages, pages);
+	if (list_empty(&movable_page_list))
 		return 0;
 
 	return migrate_longterm_unpinnable_pages(&movable_page_list, nr_pages,

@@ -34,7 +34,9 @@ void foo(void)
         DEFINE(CRED_EGID, offsetof(struct cred, egid));
         BLANK();
 
+	DEFINE(SP_OFF, offsetof(struct pt_regs, ps));
 	DEFINE(SIZEOF_PT_REGS, sizeof(struct pt_regs));
+	DEFINE(SWITCH_STACK_SIZE, sizeof(struct switch_stack));
 	DEFINE(PT_PTRACED, PT_PTRACED);
 	DEFINE(CLONE_VM, CLONE_VM);
 	DEFINE(CLONE_UNTRACED, CLONE_UNTRACED);

@@ -1615,7 +1615,7 @@ static void steam_do_deck_input_event(st
 
 	if (!(b9 & BIT(6)) && steam->did_mode_switch) {
 		steam->did_mode_switch = false;
-		cancel_delayed_work_sync(&steam->mode_switch);
+		cancel_delayed_work(&steam->mode_switch);
 	} else if (!steam->client_opened && (b9 & BIT(6)) && !steam->did_mode_switch) {
 		steam->did_mode_switch = true;
 		schedule_delayed_work(&steam->mode_switch, 45 * HZ / 100);

@@ -301,6 +301,12 @@ void io_destroy_buffers(struct io_ring_c
 	}
 }
 
+static void io_destroy_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl)
+{
+	xa_erase(&ctx->io_bl_xa, bl->bgid);
+	io_put_bl(ctx, bl);
+}
+
 int io_remove_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_provide_buf *p = io_kiocb_to_cmd(req, struct io_provide_buf);

@@ -642,12 +648,13 @@ int io_register_pbuf_ring(struct io_ring
 		/* if mapped buffer ring OR classic exists, don't allow */
 		if (bl->is_mapped || !list_empty(&bl->buf_list))
 			return -EEXIST;
-	} else {
-		free_bl = bl = kzalloc(sizeof(*bl), GFP_KERNEL);
-		if (!bl)
-			return -ENOMEM;
+		io_destroy_bl(ctx, bl);
 	}
 
+	free_bl = bl = kzalloc(sizeof(*bl), GFP_KERNEL);
+	if (!bl)
+		return -ENOMEM;
+
 	if (!(reg.flags & IOU_PBUF_RING_MMAP))
 		ret = io_pin_pbuf_ring(&reg, bl);
 	else

@@ -336,7 +336,10 @@ EXPORT_SYMBOL_GPL(vsock_find_connected_s
 
 void vsock_remove_sock(struct vsock_sock *vsk)
 {
-	vsock_remove_bound(vsk);
+	/* Transport reassignment must not remove the binding. */
+	if (sock_flag(sk_vsock(vsk), SOCK_DEAD))
+		vsock_remove_bound(vsk);
+
 	vsock_remove_connected(vsk);
 }
 EXPORT_SYMBOL_GPL(vsock_remove_sock);

@@ -820,12 +823,13 @@ static void __vsock_release(struct sock
 	 */
 	lock_sock_nested(sk, level);
 
+	sock_orphan(sk);
+
 	if (vsk->transport)
 		vsk->transport->release(vsk);
 	else if (sock_type_connectible(sk->sk_type))
 		vsock_remove_sock(vsk);
 
-	sock_orphan(sk);
 	sk->sk_shutdown = SHUTDOWN_MASK;
 
 	skb_queue_purge(&sk->sk_receive_queue);

@@ -823,13 +823,19 @@ static void __vsock_release(struct sock
 	 */
 	lock_sock_nested(sk, level);
 
-	sock_orphan(sk);
+	/* Indicate to vsock_remove_sock() that the socket is being released and
+	 * can be removed from the bound_table. Unlike transport reassignment
+	 * case, where the socket must remain bound despite vsock_remove_sock()
+	 * being called from the transport release() callback.
+	 */
+	sock_set_flag(sk, SOCK_DEAD);
 
 	if (vsk->transport)
 		vsk->transport->release(vsk);
 	else if (sock_type_connectible(sk->sk_type))
 		vsock_remove_sock(vsk);
 
+	sock_orphan(sk);
 	sk->sk_shutdown = SHUTDOWN_MASK;
 
 	skb_queue_purge(&sk->sk_receive_queue);

@@ -8,6 +8,7 @@
 #include <linux/timex.h>
 #include <linux/i8253.h>
 
+#include <asm/hypervisor.h>
 #include <asm/apic.h>
 #include <asm/hpet.h>
 #include <asm/time.h>

@@ -39,9 +40,15 @@ static bool __init use_pit(void)
 
 bool __init pit_timer_init(void)
 {
-	if (!use_pit())
+	if (!use_pit()) {
+		/*
+		 * Don't just ignore the PIT. Ensure it's stopped, because
+		 * VMMs otherwise steal CPU time just to pointlessly waggle
+		 * the (masked) IRQ.
+		 */
+		clockevent_i8253_disable();
 		return false;
-
+	}
 	clockevent_i8253_init(true);
 	global_clock_event = &i8253_clockevent;
 	return true;

@@ -108,11 +108,8 @@ int __init clocksource_i8253_init(void)
 #endif
 
 #ifdef CONFIG_CLKEVT_I8253
-static int pit_shutdown(struct clock_event_device *evt)
+void clockevent_i8253_disable(void)
 {
-	if (!clockevent_state_oneshot(evt) && !clockevent_state_periodic(evt))
-		return 0;
-
 	raw_spin_lock(&i8253_lock);
 
 	outb_p(0x30, PIT_MODE);

@@ -123,6 +120,14 @@ static int pit_shutdown(struct clock_eve
 	}
 
 	raw_spin_unlock(&i8253_lock);
+}
+
+static int pit_shutdown(struct clock_event_device *evt)
+{
+	if (!clockevent_state_oneshot(evt) && !clockevent_state_periodic(evt))
+		return 0;
+
+	clockevent_i8253_disable();
 	return 0;
 }
 

@@ -24,6 +24,7 @@ extern raw_spinlock_t i8253_lock;
 extern bool i8253_clear_counter_on_shutdown;
 extern struct clock_event_device i8253_clockevent;
 extern void clockevent_i8253_init(bool oneshot);
+extern void clockevent_i8253_disable(void);
 
 extern void setup_pit_timer(void);
 

@@ -393,11 +393,6 @@ static ssize_t vfio_platform_read_mmio(s
 
 	count = min_t(size_t, count, reg->size - off);
 
-	if (off >= reg->size)
-		return -EINVAL;
-
-	count = min_t(size_t, count, reg->size - off);
-
 	if (!reg->ioaddr) {
 		reg->ioaddr =
 			ioremap(reg->addr, reg->size);

@@ -479,11 +474,6 @@ static ssize_t vfio_platform_write_mmio(
 
 	if (off >= reg->size)
 		return -EINVAL;
-
-	count = min_t(size_t, count, reg->size - off);
-
-	if (off >= reg->size)
-		return -EINVAL;
 
 	count = min_t(size_t, count, reg->size - off);